codexer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs (SKILL.md and references/context7-usage.md) to perform web searches (#websearch) and to call Context7 MCP tools (resolve-library-id and get-library-docs) to fetch public library documentation, Stack Overflow posts, and blog content and then read/apply that content to generate code and make recommendations, so untrusted third‑party content can directly influence agent actions.